Update README.md

README.md

@@ -34,8 +34,20 @@ widget:
 
 # FLUX.1-[dev] Panorama LoRA (v2)
 
-This LoRA has been trained using random samples of Google Street View.
+A LoRA model to generate panoramas using Flux dev.
 
-Due to this and since the base model is FLUX.1-[dev], it is made available for [research purpose and demonstration only](https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev).
+It should work most of the time (see the examples), but if you ask for something rare or never seen before (a special angle, or a location eg. ins pace), it might have trouble creating the spherical distortion.
+
+## Which image ratio to use?
+
+This model has been trained on images with a 2:1 (2048x1024).
+
+However panorama viewers are pretty flexible when it comes to resolution, and FLUX.1 seems to generalize well.
+
+For instance the gallery samples have been generated in 1536 × 640 (~21:9), since this is reasonably fast (16 sec on the HF Inference API).
+
+## Licensing
+
+As the base model is FLUX.1-[dev] and since the data comes from Google Street View, it should be used for [demonstration purposes only](https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev).
 
 Please use it responsibly, thank you!